Description: In this paper the authors analyze data from group medical expense insurance claims and show that many insurance loss distributions have very 'heavy tails' because large losses represent a disproportionate fraction of the total cost. They also present a simple model to reproduce and explain the large loss behavior. From Actuarial Research Clearing House 1990, VOL. 2

Description: The purpose of this paper is to introduce a practical method for interpolation and smoothing and give a number of numerical examples using the method. The method is a variation of the Whittaker-Henderson method. Discussions of this paper are included.

Description: This is a letter to readers of The Actuary from Arnold Dicke and Walter Lowrie to solicit opinions on the problem which seems to crop up each time an examination is to be set.

Description: The paper gives two criteria for fit and uses two different criteria to transform an initial graduation into one with better fit. It is shown that the two sets of criteria give the same transformation. The mathematical relationships between the two sets of criteria are then derived. It is clear from those relationships that when one set of criteria is small, the other set is small [but reasonably the same]. Some general comments on various measures of fit are made.

Description: The following topics were discussed at concurrent sessions: 1. Personal Security in the 1970's- United States and Canada, 2. Adjusted earnings for life companies, 3. Pension funding, 4. What about these younger actuaries?, 5. Sources of statistical information for actuaries, 6. Variable life insurance, 7. Models and decision techniques, and 8. Role of the actuary in expense control. From Transactions of Society of Actuaries 1970, Vol 22, Pt. 2, No. 63.

Description: This paper deals with the policy reserves for future benefits that arise under retrospectively experience-rated group insurance policies. The reserves discussed are true policy-year reserves and should not be confused with the statutory rating refund liability, which represents the amount of the current policy year's dividend or experience rating refund earned between the last policy anniversary and December 31.From Transactions of Society of Actuaries 1983, Vol. 35.

Description: In this paper, methods are presented that allow the systematic graduation of multidimensional data subject to linear constraints. With these constraints the practitioner can impose limitations on the graduation that agree with prior knowledge. Discussions of this paper are included.